Maps

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and interprets live place and routing data from public endpoints (see "External Endpoints" e.g., https://maps.googleapis.com, https://nominatim.openstreetmap.org, https://api.mapbox.com) and uses those third-party results to make provider, routing, and launch decisions, exposing the agent to untrusted/user-generated content that can influence actions.